Package org.archive.modules.extractor

Examples of org.archive.modules.extractor.LinkContext$SimpleLinkContext

292
293
294
295
296
297
298
299
300
301
        String pathFromSeed = (args.length > 1)?
            args[1].toString() : "";
        UURI via = (args.length > 2 && args[2].length()>1) ?
            UURIFactory.getInstance(args[2].toString()):
            null;
        LinkContext viaContext = (args.length > 3 && args[2].length()>1) ?
                HTMLLinkContext.get(args[3].toString()): null;
        CrawlURI caUri = new CrawlURI(u, pathFromSeed, via, viaContext);
        return caUri;
    }
View Full Code Here
257
258
259
260
261
262
263
264
265
266
267
            return curi.getClassKey(); // should never happen
        }
    }
   
    protected void createFormSubmissionAttempt(CrawlURI curi, HTMLForm templateForm, String formProvince) {
        LinkContext lc = new LinkContext.SimpleLinkContext("form/@action");
        try {
            String submitUrl = templateForm.getAction() == null ? curi.getURI() : templateForm.getAction();
           
            CrawlURI submitCuri = curi.createCrawlURI(submitUrl, lc, Hop.SUBMIT);
            submitCuri.setFetchType(FetchType.HTTP_POST);
View Full Code Here
TOP

Related Classes of org.archive.modules.extractor.LinkContext$SimpleLinkContext

  • org.archive.modules.CrawlURI
  • org.archive.modules.forms.FormLoginProcessor
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.